FLICKER: A Fine-Grained Contribution-Aware Accelerator for Real-Time 3D Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ou, Wenhui, Wu, Zhuoyu, Zhang, Yipu, Wu, Dongjun, Hong, Freddy Ziyang, Yue, Chik Patrick
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910036987478016
author Ou, Wenhui
Wu, Zhuoyu
Zhang, Yipu
Wu, Dongjun
Hong, Freddy Ziyang
Yue, Chik Patrick
author_facet Ou, Wenhui
Wu, Zhuoyu
Zhang, Yipu
Wu, Dongjun
Hong, Freddy Ziyang
Yue, Chik Patrick
contents Recently, 3D Gaussian Splatting (3DGS) has emerged as a mainstream rendering technique due to its photorealistic quality and low latency. However, processing massive numbers of non-contributing Gaussian points introduces significant computational overhead on resource-limited edge platforms, limiting its deployment in next-generation AR/VR devices. Contribution-based prior skipping alleviates this inefficiency, yet the resulting contribution-testing workload becomes prohibitive for edge execution. In this paper, we present FLICKER, a contribution-aware 3DGS accelerator based on hardware-software co-design. The proposed framework integrates adaptive leader pixels, pixel-rectangle grouping, hierarchical Gaussian testing, and a mixed-precision architecture to enable near pixel-level, contribution-driven rendering with minimal overhead. Experimental results demonstrate up to $1.5\times$ speedup, $2.6\times$ improvement in energy efficiency, and $14%$ area reduction compared with a state-of-the-art accelerator. Compared with a representative edge GPU, FLICKER achieves a $19.8\times$ speedup and $26.7\times$ higher energy efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2603_01158
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FLICKER: A Fine-Grained Contribution-Aware Accelerator for Real-Time 3D Gaussian Splatting
Ou, Wenhui
Wu, Zhuoyu
Zhang, Yipu
Wu, Dongjun
Hong, Freddy Ziyang
Yue, Chik Patrick
Hardware Architecture
Recently, 3D Gaussian Splatting (3DGS) has emerged as a mainstream rendering technique due to its photorealistic quality and low latency. However, processing massive numbers of non-contributing Gaussian points introduces significant computational overhead on resource-limited edge platforms, limiting its deployment in next-generation AR/VR devices. Contribution-based prior skipping alleviates this inefficiency, yet the resulting contribution-testing workload becomes prohibitive for edge execution. In this paper, we present FLICKER, a contribution-aware 3DGS accelerator based on hardware-software co-design. The proposed framework integrates adaptive leader pixels, pixel-rectangle grouping, hierarchical Gaussian testing, and a mixed-precision architecture to enable near pixel-level, contribution-driven rendering with minimal overhead. Experimental results demonstrate up to $1.5\times$ speedup, $2.6\times$ improvement in energy efficiency, and $14%$ area reduction compared with a state-of-the-art accelerator. Compared with a representative edge GPU, FLICKER achieves a $19.8\times$ speedup and $26.7\times$ higher energy efficiency.
title FLICKER: A Fine-Grained Contribution-Aware Accelerator for Real-Time 3D Gaussian Splatting
topic Hardware Architecture
url https://arxiv.org/abs/2603.01158